a931cb03f8
Exporters: - postgres_exporter: DB connections, transactions, cache hit ratio, query stats - node_exporter: host CPU, memory, disk, network - cAdvisor: per-container CPU and memory usage PostgreSQL: - Enable pg_stat_statements for query-level performance tracking - Track index scans vs sequential scans, cache hit ratio Dashboard (service-health.json): - DB: connections, size, transactions/s, slow queries, cache hit ratio, index usage - Host: disk gauge, CPU, memory, network I/O, disk I/O - BRouter: request latency p50/p95/p99, container CPU + memory - All containers: CPU and memory comparison Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
121 lines
No EOL
2.6 KiB
JSON
121 lines
No EOL
2.6 KiB
JSON
{
|
|
"title": "trails.cool Overview",
|
|
"uid": "trails-overview",
|
|
"timezone": "browser",
|
|
"refresh": "30s",
|
|
"panels": [
|
|
{
|
|
"title": "Request Rate",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(http_request_duration_seconds_count[5m])) by (job)",
|
|
"legendFormat": "{{job}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Error Rate",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(http_request_duration_seconds_count{status=~\"5..\"}[5m])) / sum(rate(http_request_duration_seconds_count[5m])) * 100",
|
|
"legendFormat": "Error %"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Latency p50 / p95 / p99",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p50"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p95"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p99"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Health Status",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "up",
|
|
"legendFormat": "{{job}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "DOWN",
|
|
"color": "red"
|
|
},
|
|
"1": {
|
|
"text": "UP",
|
|
"color": "green"
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |